From 6855ca1147954cf90f1acf2eca21491d29ddf4c3 Mon Sep 17 00:00:00 2001 From: Henrik Bakke Dukefoss Date: Mon, 9 Nov 2026 10:04:08 +0100 Subject: [PATCH 1/2] docs: document Standard Compute OpenAI-compatible gateway setup Co-Authored-By: Claude Opus 5.5 --- docs/local-openai-compatible-providers.md | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/docs/local-openai-compatible-providers.md b/docs/local-openai-compatible-providers.md index 7bd335d46d..9626fce143 100644 --- a/docs/local-openai-compatible-providers.md +++ b/docs/local-openai-compatible-providers.md @@ -191,6 +191,29 @@ curl -sS "https://api.uberllm.dev/v1/models" \ | jq -r '.data[] | "\(.id)\t\(.max_output_tokens)"' ``` +## Standard Compute + +[Standard Compute](https://standardcompute.com) is an OpenAI-compatible gateway. Set `OPENAI_BASE_URL` to `https://api.stdcmpt.com/v1` and `OPENAI_API_KEY` to your Standard Compute key. + +```bash +export STANDARDCOMPUTE_API_KEY="your-standardcompute-api-key" +export OPENAI_BASE_URL="https://api.stdcmpt.com/v1" +export OPENAI_API_KEY="$STANDARDCOMPUTE_API_KEY" +claw --model "local/StandardCompute" prompt "Reply exactly HELLO_WORLD_123" +``` + +`StandardCompute` is the routed model: each request goes to the cheapest enabled model that can handle it, with automatic fallback. It is a bare name on a remote gateway, so it needs the `local/` hatch, which selects the OpenAI-compatible transport and is removed before the request. + +To pin one model, use a vendor-prefixed id from the catalog with the same hatch, for example `--model "local/deepseek/deepseek-v4-flash"`. A bare vendor prefix can pick a native route instead of the gateway. + +The public model list does not need a key: + +```bash +curl -sS "https://api.stdcmpt.com/v1/models" | jq -r '.data[].id' +``` + +See the [Standard Compute docs](https://docs.standardcompute.com) for keys and account setup. + ## Local skills install from disk Skills are discovered from Claw skill roots such as `.claw/skills/` in a workspace and `~/.claw/skills/` for user-level installs. Legacy `.codex/skills/` roots may also be scanned for compatibility, but new local Claw projects should prefer `.claw/skills/`. From 56ae7580743a7c5d2a239cd75cfe24f4c57612ca Mon Sep 17 00:00:00 2001 From: Henrik Bakke Dukefoss Date: Mon, 9 Nov 2026 12:13:31 +0100 Subject: [PATCH 2/2] docs: align Standard Compute routing sentence with its docs Co-Authored-By: Claude Opus 5.5 --- docs/local-openai-compatible-providers.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/local-openai-compatible-providers.md b/docs/local-openai-compatible-providers.md index 9626fce143..6199f0aac8 100644 --- a/docs/local-openai-compatible-providers.md +++ b/docs/local-openai-compatible-providers.md @@ -202,7 +202,7 @@ export OPENAI_API_KEY="$STANDARDCOMPUTE_API_KEY" claw --model "local/StandardCompute" prompt "Reply exactly HELLO_WORLD_123" ``` -`StandardCompute` is the routed model: each request goes to the cheapest enabled model that can handle it, with automatic fallback. It is a bare name on a remote gateway, so it needs the `local/` hatch, which selects the OpenAI-compatible transport and is removed before the request. +`StandardCompute` is the routed model: the router picks from the models enabled on your account using your quality preference, so harder tasks go to stronger models and simpler ones to cheaper models ([routing docs](https://docs.standardcompute.com/models#smart-routing)). It is a bare name on a remote gateway, so it needs the `local/` hatch, which selects the OpenAI-compatible transport and is removed before the request. To pin one model, use a vendor-prefixed id from the catalog with the same hatch, for example `--model "local/deepseek/deepseek-v4-flash"`. A bare vendor prefix can pick a native route instead of the gateway.